Improvement of Load Balancing Method in a Distributed Web System Using DNS

Progress of virtualization technology in recent years made it easy to build virtual servers on cloud. They can be used as cache server for load balancing. However, expected responsiveness cannot be gained with insufficient cache servers against load. In contrast, costs will increase by surplus cache servers against load. Therefore, we have been developing a distributed web system that adjust the number of cache servers according to load of them to reduce running cost. In this study, a load balancing method using DNS round-robin is now developed. However, load imbalance occurs among the servers with this method and responsiveness decreases because it is difficult to distribute the load uniformly using DNS roundrobin. Therefore, we implement a function to suspend the allocation of requests to the overloaded server. This paper describes improvement of load balancing method and evaluation of it. From results of experiments, we confirm that improved function is possible to prevent lowering responsiveness with lower TTL value.